A Retrospective Evaluation of Borsa Istanbul Using a Machine Learning Data Analysis Approach

Abstract

This study conducts a detailed examination of Borsa Istanbul Review (BIR) from 2013 to 2023, employing bib liometric analysis, regression analysis, and structural topic modeling (STM) to explore its scholarly impact, authorship patterns, and thematic evolution. Our bibliometric analysis reveals a significant increase in BIR’s publication volume and citation count, as well as a marked expansion in its author collaboration network, with notable contributions from Turkish and East Asian scholars. Through regression analysis, we identify several factors—such as article length, age, position in the issue (lead article status), regional author affiliation, title characteristics (length and novelty), and the presence of multiple authors, keywords, figures, and tables—as significant determinants of citation rates. Furthermore, STM reveals ten dominant themes in BIR, highlighting key focus areas, such as firm dynamics, market and country growth, financial health, and stock market returns. This comprehensive analysis sheds light on BIR’s evolving scholarly landscape and offers valuable insights for its editorial board, stakeholders, and the broader academic community interested in finance and economics. This enhanced understanding of BIR’s trends and themes is a crucial resource for navigating the wider finance research domain.